© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 88600
    Prev
    Next
    INDEX
    Explanations

    audio file path and focus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    et
    0.91
    og
    0.79
    ى
    0.79
    ot
    0.75
    ون
    0.71
    <0x80>
    0.70
    و
    0.68
    il
    0.65
    os
    0.65
    т
    0.63
    POSITIVE LOGITS
    الہ
    0.67
    締め
    0.66
    ી
    0.66
     reinterpret
    0.65
     observability
    0.64
     influent
    0.64
     ﺍ
    0.64
    کس
    0.63
    illance
    0.63
     incidental
    0.63
    Activations Density 0.003%

    No Known Activations